S
Semih Günel
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 18
Citations - 355
Semih Günel is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Pose & 3D pose estimation. The author has an hindex of 6, co-authored 14 publications receiving 167 citations. Previous affiliations of Semih Günel include MIND Institute.
Papers
More filters
Journal ArticleDOI
DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila.
TL;DR: DeepFly3D is presented, a software that infers the 3D pose of tethered, adult Drosophila using multiple camera images, and demonstrates more accurate unsupervised behavioral embedding using 3D joint angles rather than commonly used 2D pose data.
Posted ContentDOI
DeepFly3D: A deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila
TL;DR: DeepFly3D, a computational pipeline for inferring the 3D pose of tethered, adult Drosophila using multiple camera images is presented and it is demonstrated that unsupervised behavioral embedding of 3D joint angles yields more accurate behavioral maps than those generated with 2D pose data because the latter are highly perspective-dependent.
Proceedings ArticleDOI
Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
TL;DR: In this article, an unpaired image translation framework is proposed to train a pose estimator on the target domain by transferring readily available body keypoint locations from the source domain to generated target images.
Proceedings ArticleDOI
What Face and Body Shapes Can Tell Us About Height
TL;DR: A new human-height dataset is created, three magnitudes larger than existing ones, by mining explicit height labels and propagating them to additional images through face recognition and assignment consistency, and it is shown that height can only be estimated with large uncertainty.
Journal ArticleDOI
LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals.
Adam Gosztolai,Semih Günel,Semih Günel,Victor Lobato-Ríos,Marco Pietro Abrate,Daniel Morales,Helge Rhodin,Pascal Fua,Pavan Ramdya +8 more
TL;DR: LIFTPose3D as mentioned in this paper reconstructs 3D pose from a single 2D camera view by reconstructing 3D poses from two-dimensional data or from limited 3D data.